TestSetup

Exploratory analysis of Retail Trade Sales

Goals

• Reproduce the Index of the Canadian Economic Dashboard and COVID-19
• Identify data tables and vectors for the dashboard

Comments

• Time series from Canadian Economic Dashboard and COVID-19 at https://www150.statcan.gc.ca/n1/pub/71-607-x/71-607-x2020009-eng.htm
• There are 16 indicators

suppressMessages(library(cansim))
suppressMessages(library(ggplot2))
suppressMessages(library(dplyr))
suppressMessages(library(plotly))
source("../../src/utils.R")

Extract the Data

vector_names <- c(
  "v65201210", "v41690973", "v2062809", "v1001827265",
  "v1001826653", "v52367097", "v4391505", "v800450",
  "v32858858", "v32858865", "v32858872", "v74869", "v129449",
  "v129460", "v129472", "v129482"
)
length(vector_names)

[1] 16

vector_descr <- c(
  "RealGDP", "CPI", "Employment [pers]", "Int. merchendise trade Exp. [$]",
  "Int. merchendise trade Imp. [$]", "Retail Sales [$]", "hours worked",
  "Manufact. sales [$]", "Aircraft domestic [#]", "Aircraft transborder [#]",
  "Aircraft int other [#]", "Railway carloads [tons]", "Travelers US [pers]",
  "Travelers other country [pers]", "CA resident US [pers]",
  "CAresident other country [pers]"
)
names(vector_descr) <- vector_names

I expect this date to be before the start of all time series/vectors.

start_date <- "1900-01-01"

Retrieve all vectors. They are concatunated along axis 0.

vectors <- get_cansim_vector(vector_names, start_date)
dim(vectors)

[1] 7559    9

Preprocessing

Normalization all indicators so that December 2019 = 100

colnames(vectors) <- sapply(colnames(vectors), tolower)
colnames(vectors) 

[1] "decimals"      "value"         "ref_date"      "releasetime"   "symbol"        "frequencycode" "scalar_id"     "coordinate"   
[9] "vector"       

vectors$ref_date = as.Date(vectors$ref_date)

head(vectors)

vector_names[1]

[1] "v65201210"

length(vector_names)

[1] 16

indicators1 <- vector(length=16)
for (i in 1:length(vector_names)) {
  indicator = filter(vectors, vector == vector_names[i])
  ref_value = indicator$value[indicator$ref_date == as.Date('2019-12-01')]
  indicator$value_index = 100. * indicator$value/ref_value
  if (i == 1) {indicators = indicator}
  else {indicators <- rbind(indicators, indicator)}
}

head(indicators)

indicators$descr <- sapply(indicators$vector, function(x) {
  vector_descr[x][[1]]
})

Canadian Economic Dashboard Visualization

p <- ggplot(indicators, aes(x=ref_date, y=value_index)) + geom_line((aes(group=descr, color=descr))) +
  scale_x_date(date_breaks="2 month", date_labels="%b %Y", limits = as.Date(c('2019-01-01','2020-06-01'))) + scale_y_continuous(breaks=seq(0, 180,20), limits= c(0, 180)) + labs(title='Index, December 2019=100', x='', y='')
ggplotly(p)